• Home
      • Back
      • Create an account
      • Login Form
  • Product
      • Back
      • Overview
      • Product
      • Screenshots
      • Industrial portal
      • License
      • Latest version
      • Overview of versions
      • Awards of LIFEx
      • LIFEx analytics
  • Downloads
      • Back
      • Create an account
      • Download
  • Resources
      • Back
      • Overview
      • Documentation
      • Publications - Journal papers
      • How to cite LIFEx?
      • Data files
      • Open sources (registered account)
  • Support
      • Back
      • Radiomics Theory And Practice
      • Contact us !
      • FAQ of installation
      • FAQ
      • FAQ of Texture
      • Making a donation
Twitter Discord

Feature harmonization - How to correct LIFEx features for multi-scanner, multi-protocol or multi-center effect?

SeeMost radiomic features depend on the data acquisition settings, including the scanner brand, the imaging and image reconstruction, and voxel size settings. It is therefore recommended to study radiomic features from images that have been acquired using the exact same scanner and protocol settings. If this is not possible, and if you want to combine radiomic features obtained using different settings in a single analysis, some feature harmonization should be performed.
For PET and CT data, we suggest to harmonize radiomic features using the ComBat approach, that we previously validated (http://jnm.snmjournals.org/content/59/8/1321.long, https://doi.org/10.1148/radiol.2019182023), and that is freely available as a R routine : https://github.com/Jfortin1/ComBatHarmonization

We provide below an example of R script and two sample files (before and after ComBat) involving 3 features, 30 regions of interest for scanner 1 and 30 regions of interest for scanner 2. The code corresponds to using ComBat without any covariate. Before ComBat, the statistical distributions of the 3 features are quite different between scanner 1 (pink) and scanner 2 (cyan) (top row), while after ComBat, the distributions from the two scanners better match for the 3 features.

The application is described here: : https://hal.archives-ouvertes.fr/hal-02945627/file/Manuscrit_HAL.pdf
 
A tutorial is available in the electronic supplementary materials (ESM7) with examples of files to put in input (ESM2 to ESM6): 
https://link.springer.com/article/10.1007/s00330-020-07284-9

CombaTool is available here: https://forlhac.shinyapps.io/Shiny_ComBat

A guide to ComBat harmonization of imaging biomarkers in multicenter studies is available here: https://jnm.snmjournals.org/content/63/2/172.abstract

Login Form

  • Forgot your password?
  • Forgot your username?
  • Create an account
© LITO 2022 - 2025
Developed by
C. Nioche, Inserm
  • Cookie Policy
  • GDPR
Back to top
  1. You are here:  
  2. Home
  3. Resources
  4. Texture
  5. Feature harmonization